RESUMO
Developing new therapeutic strategies to target specific molecular pathways has become a primary focus in modern drug discovery science. Fibroblast growth factor receptor 2 (FGFR2) is a critical signaling protein involved in various cellular processes and implicated in numerous diseases, including cancer. Existing FGFR2 inhibitors face limitations like drug resistance and specificity issues. In this study, we present an integrated structure-based bioinformatics analysis to explore the potential of FGFR2 inhibitors-like compounds from the PubChem database with the Tanimoto threshold of 80%. We conducted a structure-based virtual screening approach on a dataset comprising 2336 compounds sourced from the PubChem database. Primarily, the selection of promising compounds was based on several criteria, such as drug-likeness, binding affinities, docking scores, and selectivity. Further, we conducted all-atom molecular dynamics (MD) simulations for 200 ns, followed by an essential dynamics analysis. Finally, a promising FGFR2 inhibitor with PubChem CID:507883 (1-[7-(1H-benzimidazol-2-yl)-4-fluoro-1H-indol-3-yl]-2-(4-benzoylpiperazin-1-yl)ethane-1,2-dione) was screened out from the study. This compound indicates a higher potential for inhibiting FGFR2 than the control inhibitor, Zoligratinib. The identified compound, CID:507883 shows >80% structural similarity with Zoligratinib. ADMET analysis showed promising pharmacokinetic potential of the screened compound. Overall, the findings indicate that the compound CID:507883 may have promising potential to serve as a lead candidate against FGFR2 and could be further exploited in therapeutic development.
Assuntos
Simulação de Acoplamento Molecular , Simulação de Dinâmica Molecular , Receptor Tipo 2 de Fator de Crescimento de Fibroblastos , Receptor Tipo 2 de Fator de Crescimento de Fibroblastos/antagonistas & inibidores , Receptor Tipo 2 de Fator de Crescimento de Fibroblastos/química , Receptor Tipo 2 de Fator de Crescimento de Fibroblastos/metabolismo , Humanos , Inibidores de Proteínas Quinases/química , Inibidores de Proteínas Quinases/farmacologia , Ligação Proteica , Desenvolvimento de Medicamentos , Relação Estrutura-AtividadeRESUMO
Introduction: Drugs that target reactive oxygen species (ROS) metabolism have progressed the treatment of pancreatic cancer treatment, yet their efficacy remains poor because of the adaptation of cancer cells to high concentration of ROS. Cells cope with ROS by recognizing 8-oxoguanine residues and processing severely oxidized RNA, which make it feasible to improve the efficacy of ROS-modulating drugs in pancreatic cancer by targeting 8-oxoguanine regulators. Methods: Poly(rC)-binding protein 1 (PCBP1) was identified as a potential oncogene in pancreatic cancer through datasets of The Cancer Genome Atlas (TCGA) project and Gene Expression Omnibus (GEO). High-throughput virtual screening was used to screen out potential inhibitors for PCBP1. Computational molecular dynamics simulations was used to verify the stable interaction between the two compounds and PCBP1 and their structure-activity relationships. In vitro experiments were performed for functional validation of silychristin. Results: In this study, we identified PCBP1 as a potential oncogene in pancreatic cancer. By applying high-throughput virtual screening, we identified Compound 102 and Compound 934 (silychristin) as potential PCBP1 inhibitors. Computational molecular dynamics simulations and virtual alanine mutagenesis verified the structure-activity correlation between PCBP1 and the two identified compounds. These two compounds interfere with the PCBP1-RNA interaction and impair the ability of PCBP1 to process RNA, leading to intracellular R loop accumulation. Compound 934 synergized with ROS agent hydrogen peroxide to strongly improve induced cell death in pancreatic cancer cells. Discussion: Our results provide valuable insights into the development of drugs that target PCBP1 and identified promising synergistic agents for ROS-modulating drugs in pancreatic cancer.
RESUMO
Identification of high-quality hit chemical matter is of vital importance to the success of drug discovery campaigns. However, this goal is becoming ever harder to achieve as the targets entering the portfolios of pharmaceutical and biotechnology companies are increasingly trending towards novel and traditionally challenging to drug. This demand has fuelled the development and adoption of numerous new screening approaches, whereby the contemporary hit identification toolbox comprises a growing number of orthogonal and complementary technologies including high-throughput screening, fragment-based ligand design, affinity screening (affinity-selection mass spectrometry, differential scanning fluorimetry, DNA-encoded library screening), as well as increasingly sophisticated computational predictive approaches. Herein we describe how an integrated strategy for hit discovery, whereby multiple hit identification techniques are tactically applied, selected in the context of target suitability and resource priority, represents an optimal and often essential approach to maximise the likelihood of identifying quality starting points from which to develop the next generation of medicines.
RESUMO
Inhibition of carbohydrate digestive enzymes is a key focus across diverse fields, given the prominence of α-glucosidase inhibitors as preferred oral hypoglycaemic drugs for diabetes treatment. ß-conglycinin is the most abundant functional protein in soy; however, it is unclear whether the peptides produced after its gastrointestinal digestion exhibit α-glucosidase inhibitory properties. Therefore, we examined the α-glucosidase inhibitory potential of soy peptides. Specifically, ß-conglycinin was subjected to simulated gastrointestinal digestion by enzymatically cleaving it into 95 peptides with gastric, pancreatic and chymotrypsin enzymes. Eight soybean peptides were selected based on their predicted activity; absorption, distribution, metabolism, excretion and toxicity score; and molecular docking analysis. The results indicated that hydrogen bonding and electrostatic interactions play important roles in inhibiting α-glucosidase, with the tripeptide SGR exhibiting the greatest inhibitory effect (IC50 = 10.57 µg/mL). In vitro studies revealed that SGR markedly improved glucose metabolism disorders in insulin-resistant HepG2 cells without affecting cell viability. Animal experiments revealed that SGR significantly improved blood glucose and decreased maltase activity in type 2 diabetic zebrafish larvae, but it did not result in the death of zebrafish larvae. Transcriptomic analysis revealed that SGR exerts its anti-diabetic and hypoglycaemic effects by attenuating the expression of several genes, including Slc2a1, Hsp70, Cpt2, Serpinf1, Sfrp2 and Ggt1a. These results suggest that SGR is a potential food-borne bioactive peptide for managing diabetes.
RESUMO
Drug discovery is costly and time consuming, and modern drug discovery endeavors are progressively reliant on computational methodologies, aiming to mitigate temporal and financial expenditures associated with the process. In particular, the time required for vaccine and drug discovery is prolonged during emergency situations such as the coronavirus 2019 pandemic. Recently, the performance of deep learning methods in drug virtual screening has been particularly prominent. It has become a concern for researchers how to summarize the existing deep learning in drug virtual screening, select different models for different drug screening problems, exploit the advantages of deep learning models, and further improve the capability of deep learning in drug virtual screening. This review first introduces the basic concepts of drug virtual screening, common datasets, and data representation methods. Then, large numbers of common deep learning methods for drug virtual screening are compared and analyzed. In addition, a dataset of different sizes is constructed independently to evaluate the performance of each deep learning model for the difficult problem of large-scale ligand virtual screening. Finally, the existing challenges and future directions in the field of virtual screening are presented.
RESUMO
BACKGROUND: Human neutrophil elastase (HNE) is an important contributor to lung diseases such as acute lung injury (ALI) or acute respiratory distress syndrome. Therefore, this study aimed to identify natural HNE inhibitors with anti-inflammatory activity through machine learning algorithms, in vitro assays, molecular dynamic simulation, and an in vivo ALI assay. METHODS: Based on the optimized Discovery Studio two-dimensional molecular descriptors, combined with different molecular fingerprints, six machine learning models were established using the Naïve Bayesian (NB) method to identify HNE inhibitors. Subsequently, the optimal model was utilized to screen 6,925 drug-like compounds obtained from the Traditional Chinese Medicine Systems Pharmacy Database and Analysis Platform (TCMSP), followed by ADMET analysis. Finally, 10 compounds with reported anti-inflammatory activity were selected to determine their inhibitory activities against HNE in vitro, and the compounds with the best activity were selected for a 100 ns molecular dynamics simulation and its anti-inflammatory effect was evaluated using Poly(I:C)-induced ALI model. RESULTS: The evaluation of the in vitro HNE inhibition efficiency of the 10 selected compounds showed that the flavonoid tricetin had the strongest inhibitory effect on HNE. The molecular dynamics simulation indicated that the binding of tricetin to HNE was relatively stable throughout the simulation. Importantly, in vivo experiments indicated that tricetin treatment substantially improved the Poly(I:C)-induced ALI. CONCLUSION: The proposed NB model was proved valuable for exploring novel HNE inhibitors, and natural tricetin was screened out as a novel HNE inhibitor, which was confirmed by in vitro and in vivo assays for its inhibitory activities.
RESUMO
Hundreds of virtual screening (VS) studies have targeted the severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) main protease (M-pro) to identify small molecules that inhibit its proteolytic action. Most studies use AutoDock Vina or Glide methodologies [high-throughput VS (HTVS), standard precision (SP), or extra precision (XP)], independently or in a VS workflow. Moreover, the Protein Data Bank (PDB) includes multiple complexes between M-pro and various noncovalent ligands, providing an excellent benchmark for assessing the predictive capabilities of docking programs. Here, we analyze the ability of the three Glide methodologies and AutoDock Vina by using various target structures/preparations to predict the experimental poses of these complexes. Our aims are to optimize target setup and docking methodologies, minimize false positives, and maximize the identification of various chemotypes in a SARS-CoV-2 M-pro noncovalent inhibitor VS campaign.
RESUMO
Patients diagnosed with rare diseases and their and families search desperately to organize drug discovery campaigns. Alternative models that differ from default paradigms offer real opportunities. There are, however, no clear guidelines for the development of such models, which reduces success rates and raises costs. We address the main challenges in making the discovery of new preclinical treatments more accessible, using rare hereditary paraplegia as a paradigmatic case. First, we discuss the necessary expertise, and the patients' clinical and genetic data. Then, we revisit gene therapy, de novo drug development, and drug repurposing, discussing their applicability. Moreover, we explore a pool of recommended in silico tools for pathogenic variant and protein structure prediction, virtual screening, and experimental validation methods, discussing their strengths and weaknesses. Finally, we focus on successful case applications.
RESUMO
In this study, we screened novel dipeptidyl peptidase IV (DPP4) inhibitors from the ConMedNP library consisting of 3507 molecules. Interestingly, molecular docking, ADMET, and the anti-diabetic activity predictions suggest that three molecules, namely OTH_UD_XX06_1, GB19, and BMC_000104, have a high binding affinity toward DPP4. The molecular dynamics (MD) simulation results suggest that these hit molecules have a stable binding pose and occupy the binding pockets throughout the 200 ns simulation. The presence of intermolecular H-bonding between the ligands and DPP4 was observed throughout the simulation period. Thus, docking and MD results, predicted that the three compounds were the most potent DPP4 inhibitors that could putatively bind to the DPP4 active site via both conventional H-bonding and hydrophobic interactions. These results could aid the discovery of new drugs to treat type 2 diabetes.
RESUMO
In this work, we report the identification of novel bromodomain-containing protein 9 (BRD9) binders through a virtual screening based on our developed 3D structure-based pharmacophore model. The in silico workflow here described led to the identification of a promising initial hit (1) featuring the 1-ethyl-1H-pyrazolo[3,4-b]pyridine motif which represented an unexplored chemotype for the development of a new class of BRD9 ligands. The encouraging biophysical results achieved for compound 1 prompted us to explore further tailored structural modification around the C-4 and C-6 positions of the central core. Hence, the design and synthesis of a set of 19 derivatives (2-20) were performed to extensively investigate the chemical space of BRD9 binding site. Among them, four compounds (5, 11, 12, and 19) stood out in biophysical assays as new valuable BRD9 ligands featuring IC50 values in the low-micromolar range. Noteworthy, a promising antiproliferative activity was detected in vitro for compound 5 on HeLa and A375 cancer cell line. The successful combination and application of in silico tools, chemical synthesis, and biological assays allowed to identify novel BRD9 binders and to expand the arsenal of promising chemical entities amenable to the recognition of this important epigenetic target.
RESUMO
Aim: The purpose of this study is to design and synthesize a series of novel chalcone amide α-glucosidase (AG) inhibitors (L1-L10) based on virtual screening and molecular dynamics (MD) simulation. Materials & methods: Target compounds (L1-L10) were synthesized from 2-hydroxyacetophenone and methyl 4-formylbenzoate. Results: In vitro activity test shows that most compounds have good AG inhibition. Specially, compound L4 (IC50 = 8.28 ± 0.04 µM) had the best inhibitory activity, superior to positive control acarbose (IC50 = 8.36 ± 0.02 µM). Molecular docking results show that the good potency of L4 maybe attributed to strong interactions between chalcone skeleton and active site, and the torsion of carbon nitrogen bond in amide group. Conclusion: Compound L4 maybe regard as a good anti-Type II diabetes candidate to preform further study.
[Box: see text].
Assuntos
Amidas , Desenho de Fármacos , Inibidores de Glicosídeo Hidrolases , Simulação de Acoplamento Molecular , alfa-Glucosidases , Inibidores de Glicosídeo Hidrolases/farmacologia , Inibidores de Glicosídeo Hidrolases/síntese química , Inibidores de Glicosídeo Hidrolases/química , alfa-Glucosidases/metabolismo , Amidas/química , Amidas/farmacologia , Amidas/síntese química , Relação Estrutura-Atividade , Estrutura Molecular , Humanos , Simulação de Dinâmica Molecular , Chalcona/química , Chalcona/farmacologia , Chalcona/síntese químicaRESUMO
In consideration of several serious side effects induced by the classical AF-2 involved "lock" mechanism, recently disclosed PPARγ-Ser273 phosphorylation mode of action has become an alternative and mainstream mechanism for currently PPARγ-based drug discovery and development with an improved therapeutic index. In this study, by virtue of structure-based virtual high throughput screening (SB-VHTS), structurally chemical optimization by targeting the inhibition of the PPARγ-Ser273 phosphorylation as well as in vitro biological evaluation, which led to the final identification of a chrysin-based potential hit (YGT-31) as a novel selective PPARγ modulator with potent binding affinity and partial agonism. Further in vivo evaluation demonstrated that YGT-31 possessed potent glucose-lowering and relieved hepatic steatosis effects without involving the TZD-associated side effects. Mechanistically, YGT-31 presented such desired therapeutic index, mainly because it effectively inhibited the CDK5-mediated PPARγ-Ser273 phosphorylation, selectively elevated the level of insulin sensitivity-related Glut4 and adiponectin but decreased the expression of insulin-resistance-associated genes PTP1B and SOCS3 as well as inflammation-linked genes IL-6, IL-1ß and TNFα. Finally, the molecular docking study was also conducted to uncover an interesting hydrogen-bonding network of YGT-31 with PPARγ-Ser273 phosphorylation-related key residues Ser342 and Glu343, which not only gave a clear verification for our targeting modification but also provided a proof of concept for the abovementioned molecular mechanism.
Assuntos
Fígado Gorduroso , Flavonoides , PPAR gama , PPAR gama/metabolismo , PPAR gama/agonistas , Flavonoides/farmacologia , Flavonoides/química , Flavonoides/síntese química , Relação Estrutura-Atividade , Fígado Gorduroso/tratamento farmacológico , Fígado Gorduroso/metabolismo , Humanos , Estrutura Molecular , Diabetes Mellitus Tipo 2/tratamento farmacológico , Animais , Hipoglicemiantes/farmacologia , Hipoglicemiantes/química , Hipoglicemiantes/síntese química , Simulação de Acoplamento Molecular , Relação Dose-Resposta a Droga , Camundongos , Masculino , Avaliação Pré-Clínica de MedicamentosRESUMO
Thymidylate kinase (TMK) is a pivotal enzyme in Mycobacterium tuberculosis (Mtb), crucial for phosphorylating thymidine monophosphate (dTMP) to thymidine diphosphate (dTDP), thereby playing a critical role in DNA biosynthesis. Dysregulation or inhibition of TMK activity disrupts DNA replication and cell division, making it an attractive target for anti-tuberculosis drug development. In this study, the statistically validated pharmacophore mode was developed from a set of known TMK inhibitors. Further, the robust pharmacophore was considered for screening the Enamine database. The chemical space was reduced through multiple molecular docking approaches, pharmacokinetics, and absolute binding energy estimation. Two different molecular docking algorithms favor the strong binding affinity of the proposed molecules towards TMK. Machine learning-based absolute binding energy also showed the potentiality of the proposed molecules. The binding interactions analysis exposed the strong binding affinity between the proposed molecules and active site amino residues of TMK. Several statistical parameters from all atoms MD simulation explained the stability between proposed molecules and TMK in the dynamic states. The MM-GBSA approach also found a strong binding affinity for each proposed molecule. Therefore, the proposed molecules might be crucial TMK inhibitors for managing Mtb inhibition subjected to in vitro/in vivo validations.
RESUMO
Enhancing virtual screening enrichment has become an urgent problem in computational chemistry, driven by increasingly large databases of commercially available compounds, without a commensurate drop in in vitro screening costs. Docking these large databases is possible with cloud-scale computing. However, rapid docking necessitates compromises in scoring, often leading to poor enrichment and an abundance of false positives in docking results. This work describes a new scoring function composed of two parts - a knowledge-based component that predicts the probability of a particular atom type being in a particular receptor environment, and a tunable weight matrix that converts the probability predictions into a dimensionless score suitable for virtual screening enrichment. This score, the FitScore, represents the compatibility between the ligand and the binding site and is capable of a high degree of enrichment across standardized docking test sets.
Assuntos
Aprendizado de Máquina , Simulação de Acoplamento Molecular , Ligantes , Sítios de Ligação , Humanos , Ligação Proteica , Proteínas/química , Proteínas/metabolismo , Software , Avaliação Pré-Clínica de Medicamentos/métodos , Descoberta de Drogas/métodosRESUMO
BACKGROUND: Leishmaniasis is a deadly protozoan parasitic disease and a significant health problem in underdeveloped and developing countries. The global spread of the parasite, coupled with the emergence of drug resistance and severe side effects associated with existing treatments, has necessitated the identification of new and potential drugs. OBJECTIVE: This study aimed to identify promising compounds for the treatment of leishmaniasis by targeting two essential enzymes of Leishmania donovani: trypanothione reductase (Try-R) and trypanothione synthetase (Try-S). METHODS: High-throughput virtual and in vitro screening of in-house and commercial databases was conducted. A pharmacophore model with seven features was developed and validated using the Guner-Henery method. The pharmacophore-based virtual screening yielded 690 hits, which were further filtered through Lipinski's rule, ADMET analysis, and molecular docking against Try-R and Try-S. Molecular dynamics studies were performed on selected compounds, and in vitro experiments were conducted to evaluate their activity against the promastigote and amastigote forms of L. donovani. RESULTS: The virtual screening and subsequent analysis identified 33 promising compounds. Molecular dynamics studies of two compounds (comp-1 and comp-2) demonstrated stable binding interactions with the target enzymes and high affinity. In vitro experiments revealed that 13 compounds exhibited moderate activity against both the promastigote (IC50, 41 µM-76 µM) and the amastigote (IC50, 44 µM-72 µM) forms of L. donovani. Compounds 1 and 2 showed the highest percent inhibition and the lowest IC50 values. CONCLUSION: The identified compounds demonstrated significant inhibitory activity against Leishmania donovani and stable interactions with target enzymes. These findings suggest that the compounds could serve as promising leads for developing new treatments for leishmaniasis.
RESUMO
Acetyl-coenzyme A carboxylase (ACC) and diacylglycerol acyltransferase 2 (DGAT2) are recognized as potential therapeutic targets for nonalcoholic fatty liver disease (NAFLD). Inhibitors targeting ACC and DGAT2 have exhibited the capacity to reduce hepatic fat in individuals afflicted with NAFLD. However, there are no reports of dual inhibitors targeting ACC and DGAT2 for the treatment of NAFLD. Here, we aimed to identify potential dual inhibitors of ACC and DGAT2 using an integrated in silico approach. Machine learning-based virtual screening of commercial molecule databases yielded 395,729 hits, which were subsequently subjected to molecular docking aimed at both the ACC and DGAT2 binding sites. Based on the docking scores, nine compounds exhibited robust interactions with critical residues of both ACC and DGAT2, displaying favorable drug-like features. Molecular dynamics simulations (MDs) unveiled the substantial impact of these compounds on the conformational dynamics of the proteins. Furthermore, binding free energy assessments highlighted the notable binding affinities of specific compounds (V003-8107, G340-0503, Y200-1700, E999-1199, V003-6429, V025-4981, V006-1474, V025-0499, and V021-8916) to ACC and DGAT2. The compounds proposed in this study, identified using a multifaceted computational strategy, warrant experimental validation as potential dual inhibitors of ACC and DGAT2, with implications for the future development of novel drugs targeting NAFLD.
RESUMO
Antivirulence strategy has been explored as an alternative to traditional antibiotic development. The bacterial type IV pilus is a virulence factor involved in host invasion and colonization in many antibiotic resistant pathogens. The PilB ATPase hydrolyzes ATP to drive the assembly of the pilus filament from pilin subunits. We evaluated Chloracidobacterium thermophilum PilB (CtPilB) as a model for structure-based virtual screening by molecular docking and molecular dynamics (MD) simulations. A hexameric structure of CtPilB was generated through homology modeling based on an existing crystal structure of a PilB from Geobacter metallireducens. Four representative structures were obtained from molecular dynamics simulations to examine the conformational plasticity of PilB and improve docking analyses by ensemble docking. Structural analyses after 1 µs of simulation revealed conformational changes in individual PilB subunits are dependent on ligand presence. Further, ensemble virtual screening of a library of 4,234 compounds retrieved from the ZINC15 database identified five promising PilB inhibitors. Molecular docking and binding analyses using the four representative structures from MD simulations revealed that top-ranked compounds interact with multiple Walker A residues, one Asp-box residue, and one arginine finger, indicating these are key residues in inhibitor binding within the ATP binding pocket. The use of multiple conformations in molecular screening can provide greater insight into compound flexibility within receptor sites and better inform future drug development for therapeutics targeting the type IV pilus assembly ATPase.
RESUMO
Cyclin-dependent kinase 8 (CDK8) is highly expressed in various cancers and common complex human diseases, and an important therapeutic target for drug discovery and development. The CDK8 inhibitors are actively sought after, especially among natural products. We performed a virtual screening using the ZINC library comprising approximately 90,000 natural compounds. We applied Lipinski's rule of five, absorption, distribution, metabolism, excretion, and toxicity properties, and pan-assay interference compounds filter to eliminate promiscuous binders. Subsequently, the filtered compounds underwent molecular docking to predict their binding affinity and interactions with the CDK8 protein. Interaction analysis were carried out to elucidate the interaction mechanism of the screened hits with binding pockets of the CDK8. The ZINC02152165, ZINC04236005, and ZINC02134595 were selected with appreciable specificity and affinity with CDK8. An all-atom molecular dynamic (MD) simulation followed by essential dynamics was performed for 200 ns. Taken together, the results suggest that ZINC02152165, ZINC04236005, and ZINC02134595 can be harnessed as potential leads in therapeutic development. Moreover, the binding of the molecules brings change in protein conformation in a way that blocks the ATP-binding site of the protein, obstructing its kinase activity. These new findings from natural products offer insights into the molecular mechanisms underlying CDK8 inhibition. CDK8 was previously associated with behavioral and neurological diseases such as autism spectrum disorder, and cancers, for example, colorectal, prostate, breast, and acute myeloid leukemia. Hence, we call for further research and experimental validation, and with an eye to inform future clinical drug discovery and development in these therapeutic fields.
RESUMO
BACKGROUND: Small heterocyclic compounds have been crucial in pioneering advances in type 2 diabetes treatment. There has been a dramatic increase in the pharmacological development of novel heterocyclic derivatives aimed at stimulating the activation of Glucokinase (GK). A pharmaceutical intervention for diabetes is increasingly targeting GK as a legitimate target. Diabetes type 2 compromises Glucokinase's function, an enzyme vital for maintaining the balance of blood glucose levels. Medicinal substances strategically positioned to improve type 2 diabetes management are used to stimulate the GK enzyme using heterocyclic derivatives. OBJECTIVE: The research endeavor aimed to craft novel compounds, drawing inspiration from the inherent coumarin nucleus found in nature. The goal was to evoke the activity of the glucokinase enzyme, offering a tailored approach to mitigate the undesired side effects typically associated with conventional therapies employed in the treatment of type 2 diabetes. METHODS: Coumarin, sourced from nature's embrace, unfolds as a potent and naturally derived ally in the quest for innovative antidiabetic interventions. Coumarin was extracted from a variety of botanical origins, including Artemisia keiskeana, Mallotus resinosus, Jatropha integerrima, Ferula tingitana, Zanthoxylum schinifolium, Phebalium clavatum, and Mammea siamensis. This inclusive evaluation was conducted on Muybridge's digital database containing 53,000 hit compounds. The presence of the coumarin nucleus was found in 100 compounds, that were selected from this extensive repository. Utilizing Auto Dock Vina 1.5.6 and ChemBioDraw Ultra, structures generated through this process underwent docking analysis. Furthermore, these compounds were accurately predicted online log P using the Swiss ADME algorithm. A predictive analysis was conducted using PKCSM software on the primary compounds to assess potential toxicity. RESULTS: Using Auto Dock Vina 1.5.6, 100 coumarin derivatives were assessed for docking. Glucokinase (GK) binding was significantly enhanced by most of these compounds. Based on superior binding characteristics compared with Dorzagliatin (standard GKA) and MRK (co-crystallized ligand), the top eight molecules were identified. After further evaluation through ADMET analysis of these eight promising candidates, it was confirmed that they met the Lipinski rule of five and their pharmacokinetic profile was enhanced. The highest binding affinity was demonstrated by APV16 at -10.6 kcal/mol. A comparison between the APV16, Dorzagliatin and MRK in terms of toxicity predictions using PKCSM indicated that the former exhibited less skin sensitization, AMES toxicity, and hepatotoxicity. CONCLUSION: Glucokinase is most potently activated by 100 of the compound leads in the database of 53,000 compounds that contain the coumarin nucleus. APV12, with its high binding affinity, favorable ADMET (adjusted drug metabolic equivalents), minimal toxicity, and favorable pharmacokinetic profile warrants consideration for progress to in vitro testing. Nevertheless, to uncover potential therapeutic implications, particularly in the context of type 2 diabetes, thorough investigations and in-vivo evaluations are necessary for benchmarking before therapeutic use, especially experiments involving the STZ diabetic rat model.
RESUMO
Multifactorial diseases demand therapeutics that can modulate multiple targets for enhanced safety and efficacy, yet the clinical approval of multitarget drugs remains rare. The integration of machine learning (ML) and deep learning (DL) in drug discovery has revolutionized virtual screening. This study investigates the synergy between ML/DL methodologies, molecular representations, and data augmentation strategies. Notably, we found that SVM can match or even surpass the performance of state-of-the-art DL methods. However, conventional data augmentation often involves a trade-off between the true positive rate and false positive rate. To address this, we introduce Negative-Augmented PU-bagging (NAPU-bagging) SVM, a novel semi-supervised learning framework. By leveraging ensemble SVM classifiers trained on resampled bags containing positive, negative, and unlabeled data, our approach is capable of managing false positive rates while maintaining high recall rates. We applied this method to the identification of multitarget-directed ligands (MTDLs), where high recall rates are critical for compiling a list of interaction candidate compounds. Case studies demonstrate that NAPU-bagging SVM can identify structurally novel MTDL hits for ALK-EGFR with favorable docking scores and binding modes, as well as pan-agonists for dopamine receptors. The NAPU-bagging SVM methodology should serve as a promising avenue to virtual screening, especially for the discovery of MTDLs.